Eager Execution

[behzad-nobakht]

I have a big amount of data that needs mapping before feeding to the networks. So, instead of
(X_train, y_train), (_, _) = mnist.load_data()

I will use: dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train)).batch(self.batch_size) and then use:

for imgs, labels in dataset:
    noise = tf.random.normal(shape=(self.batch_size, self.latent_dim), mean=0,stddev=1)
    d_loss = self.critic_model.train_on_batch([imgs, labels, noise], [valid, fake, dummy])

could you help me run your script under these conditions (TF Eager Executaion)? Thanks